© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13635
    Prev
    Next
    INDEX
    Explanations

    movement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Winaray
    -0.52
     Spreading
    -0.42
     sobra
    -0.42
    yl
    -0.42
     TAP
    -0.40
     PEP
    -0.40
    rent
    -0.40
     PCM
    -0.39
     Save
    -0.38
    WAN
    -0.38
    POSITIVE LOGITS
     forward
    0.91
    出版年
    0.82
    ViewImports
    0.78
    findpost
    0.76
    rrggbb
    0.76
    ReusableCell
    0.73
    帖最后由
    0.70
    SourceChecksum
    0.69
     незавершена
    0.68
    forward
    0.67
    Activations Density 0.003%

    No Known Activations